A novel Bayesian method for variable selection and estimation in binary quantile regression
Dao, Mai Wang, Min Ghosh, Souparno
Dao, Mai
Wang, Min
Ghosh, Souparno
An error occurred retrieving the object's statistics
Citations
Altmetric:
Authors
Dao, Mai
Wang, Min
Ghosh, Souparno
Wang, Min
Ghosh, Souparno
Other Names
Location
Time Period
Advisors
Original Date
Digitization Date
Issue Date
2022-07-03
Type
Article
Genre
Keywords
Binary quantile regression,Gibbs sampler,Importance sampling,Variable selection
Subjects (LCSH)
Citation
Dao, M., Wang, M., Ghosh, S., A novel Bayesian method for variable selection and estimation in binary quantile regression, Stat. Anal. Data Min.: ASA Data Sci. J.. (2022), 1– 15. https://doi.org/10.1002/sam.11591
Abstract
In this paper, we develop a Bayesian hierarchical model and associated computation strategy for simultaneously conducting parameter estimation and variable selection in binary quantile regression. We specify customary asymmetric Laplace distribution on the error term and assign quantile-dependent priors on the regression coefficients and a binary vector to identify the model configuration. Thanks to the normal-exponential mixture representation of the asymmetric Laplace distribution, we proceed to develop a novel three-stage computational scheme starting with an expectation–maximization algorithm and then the Gibbs sampler followed by an importance re-weighting step to draw nearly independent Markov chain Monte Carlo samples from the full posterior distributions of the unknown parameters. Simulation studies are conducted to compare the performance of the proposed Bayesian method with that of several existing ones in the literature. Finally, two real-data applications are provided for illustrative purposes.
Table of Contents
Description
Click on the DOI to access this article (may not be free).
Publisher
John Wiley & Sons, Ltd
Journal
Book Title
Series
Statistical Analysis and Data Mining
2022
2022
Digital Collection
Finding Aid URL
Use and Reproduction
Archival Collection
PubMed ID
DOI
ISSN
1932-1864